Give your agent a program, not a mouse.
Your agent, or a person, does a task once in an app. OpenAdapt compiles it into a program your agent can call. A healthy run makes no model calls; the program checks the record before and after each save, and stops when a check fails.

The program29 steps, compiled from one recording
Name
Date of birth and sex
Address
Phone, email and country
Create the chart
- Saved and checked 11 of 11 record checks confirmed
- Saved and checked 11 of 11 record checks confirmed
- Saved and checked 11 of 11 record checks confirmed
- Stopped before saving Possible duplicate patient
See every run, and what needs you
OpenAdapt Cloud shows how each run ended, which runs stopped for a person, a signed receipt for each checked run, and the last two weeks at a glance.
Screenshots of OpenAdapt Cloud with a fictional company and synthetic data.Open the dashboard
The program stopped before saving
a possible duplicate
On referral 4, OpenEMR listed a patient who might be the same person. The program created no chart and left the decision to a person.


The same kind of stop on an earlier run of the referral program, filmed.
The program it compiled
A recorded referral, compiled into 29 fixed steps. Four runs play through them; the fourth stops at a possible duplicate.
- For each referral in the list to Name (loop body: declared loop)
- Name to Date of birth and sex (sequence)
- Date of birth and sex to Address (sequence)
- Address to Phone, email and country (sequence)
- Phone, email and country to Create the chart (sequence)
- Create the chart to For each referral in the list, returns to an earlier step (sequence)
- For each referral in the list to Every referral done (sequence)
- Create the chart to Stop the run (exception: not confirmed)
The map follows the emitted edge targets. It keeps each loop and exception route visible.
Test copy of OpenEMR, synthetic patients. Recorded values are left out. This replay combines four separate runs; the loop drawn around them was not itself run or qualified.
How a program runs and is repaired, with a demo: How it works
It reads the saved record back
On a test copy of OpenEMR, Claude Sonnet 5.5 entered referrals on its own with computer use while we made some of the saves fail in the database. The agent reported 28 of the 30 failed saves as done. Reading the records back from the database caught all 30, and it confirmed the 5 that saved correctly. The table shows each kind of failure.
- 28 of 30
- bad saves the agent reported as done
- 30 of 30
- injected bad saves caught by reading the record back
- 0
- false alarms on clean saves
Reported as done Caught as a bad save Confirmed as saved correctly Not caught
The agent noticed none of the 30 failures. On the other 2 it also said it saved the chart, but added that it couldn’t see the whole email field. On a second run with 30 different injected failures, the read-back caught all 30 injected bad saves plus 1 bad save the agent made itself on a clean-save item (31 of 31 in all). One item in each run where the saved chart didn’t hold the email the agent typed, so the fault never fired, was also not reported as verified and is outside those denominators. Claude Sonnet 5.5 computer use alone, synthetic patients, faults injected only in the test database, 20 Nov 2026. See the runs
$0 in model fees per run. The compiled program calls no model.
Watch it catch a bad save on your computer
In about a minute, it runs a clinic app with synthetic records on your computer, makes one entry that saves and one whose save fails on purpose, and shows OpenAdapt stopping. No account, and nothing is uploaded.
uvx --python 3.12 openadapt@latest quickstart --break-itFor teams building AI agents
Your agent supplies the values, and the program enters them in the app
Your agent calls a compiled program by name. The program enters the values, reads the record back and returns the outcome.
AI agent
Ready
View call
enter_referral( fname: "Nadia", lname: "Brennan", DOB: "1971-04-19", … )
OpenAdapt step 0 of 41

- Screens sent to a model
- 0
- Model cost
- $0.00
The agent passes the fields and gets back a status. No screen goes to a model.
Sped up, synthetic patients. Agent alone is Claude Sonnet 5.5’s real runs on the same patients. Both show 7 real runs from 14 Oct, repeated to fill 25.
Start in a minute
One command for Claude Code, or a few lines of Python for your own agent.
Claude Code: one command
claude mcp add openadapt -- uvx --python 3.12 openadapt-agent serveAdds OpenAdapt to Claude Code. With no workflows of your own, it serves a sandbox workflow.
Your own agent: a few lines of Python
from openadapt_flow.jit import compile_agent
program = compile_agent(my_agent, task=task, app=app, verifier=verifier, policy=policy, model_key=key)
program.run(note="Follow up in two weeks") # first call: your agent does the task once
program.run(note="Recheck in ten days") # after a person approves: the program, no model callsYour agent does the task once. After a person approves it, OpenAdapt runs it as a program with no model calls and reads each save back.
For regulated settings, such as healthcare and insurance
OpenAdapt runs on a computer you control
It signs in to your system from there, and your records stay there. It suits work where a wrong entry is costly, such as a clinic’s charts or an insurer’s claims.
- A person decides each save
- By default, each save waits for a person, with a picture of exactly what will be saved.
- The record is read back
- After a save, OpenAdapt checks the saved fields through a separate read-only login.
- The run report is signed
- Anyone can check its signature in a browser.
OpenAdapt Desktop's phone page, 18 Oct 2026. The link to the computer is simulated; the card shows a real frame from the referral run above.
Our test runs and results, with their evidence
Our test runs use test systems and synthetic records, and each is published with its evidence. Your own runs stay private.
Sources
- OpenAdapt scoreboard, the agent's claims versus the read-back, run openemr_referral/2026-11-20-a (SCOREBOARD.md). Claude Sonnet 5.5 did the entry alone with computer use, on a local OpenEMR test copy with synthetic patients. We injected faults only in the test database, in these ways: a field blanked, a value changed, a duplicate chart, a save that never landed, another chart deleted, and another chart edited. Each fault had 5 items, and there were 5 clean items as well. By the scoreboard's success rule, the agent reported 28 of the 30 bad saves as done; on the other 2 it said it saved the chart but couldn't see the whole email field. It noticed none of the 30 failures. verify-run (openadapt-flow 3.3.0) caught 30 of the 30 injected bad saves. It confirmed 5 of 5 clean saves, with 0 false alarms. One more item, where the saved chart didn't hold the email the agent typed so the fault never fired, was also not reported as verified. A second run, openemr_referral/heldout-2026-11-20-a, used 6 different faults with three existing charts: verify-run caught 30 of 30 injected bad saves, plus 1 bad save the agent made itself on a clean-save item (31 of 31 in all), and confirmed 5 of 5 clean saves with 0 false alarms; one fault-not-reached item was also not reported as verified; in that run the agent itself reported the wrong date of birth in all 5 items where the fault moved it. The runs weren't timed.
- OpenAdapt quickstart with --break-it (openadapt launcher 1.17.0), MockMed synthetic clinic app, 18 Oct 2026 (the run's reports): the normal entry ended Done and checked by a read of the saved note; with the save rejected on purpose, the screen looked the same as the good save, and the run stopped and reported Check the record without retrying.
Pick a data-entry task your team does by hand every day
Product updates by email, or ask about a pilot.













